Learning Adaptive Correlations of Independent Components for Complex Cell Modeling

Author

Wang, Zhe ; Luo, Siwei ; Huang, Yaping

Author_Institution

Sch. of Comput. & Inf. Technol., Beijing Jiaotong Univ., Beijing, China

Volume

1

fYear

2009

fDate

7-8 Nov. 2009

Firstpage

174

Lastpage

178

Abstract

Motivated in part by the hierarchical processing of the cortex, we build an unsupervised network learning the properties of complex cells in V1. Unlike traditional methods, we model the binary relation among these complex cells, which makes our network less constrained and more adaptive for the connectivity among these cells. The obtained filters not only emerge properties similar to those of complex cells, but show more local structures than traditional method such as TICA.

Keywords

brain models; independent component analysis; unsupervised learning; adaptive correlations; binary relation; complex cell modeling; hierarchical processing; independent components; unsupervised network learning; Artificial intelligence; Band pass filters; Brain modeling; Computer networks; Gabor filters; Independent component analysis; Information technology; Instruction sets; Neurons; Nonlinear filters; adaptive correlation; binary relation; complex cells; independent component analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-4244-3835-8

Electronic_ISBN

978-0-7695-3816-7

Type

conf

DOI

10.1109/AICI.2009.281

Filename

5376075